ATLO-ML: Adaptive Time-Length Optimizer for Machine Learning -- Insights from Air Quality Forecasting
This addresses a specific bottleneck in time-series forecasting, such as for air quality prediction, by providing a flexible pre-processing tool, but it appears incremental as it adapts existing optimization concepts to temporal parameters.
The paper tackles the problem of selecting optimal input time length and sampling rate for time-series predictions in machine learning, introducing ATLO-ML, an adaptive system that automatically determines these parameters based on user-defined output time length, and results show it significantly improves model accuracy compared to fixed time lengths.
Accurate time-series predictions in machine learning are heavily influenced by the selection of appropriate input time length and sampling rate. This paper introduces ATLO-ML, an adaptive time-length optimization system that automatically determines the optimal input time length and sampling rate based on user-defined output time length. The system provides a flexible approach to time-series data pre-processing, dynamically adjusting these parameters to enhance predictive performance. ATLO-ML is validated using air quality datasets, including both GAMS-dataset and proprietary data collected from a data center, both in time series format. Results demonstrate that utilizing the optimized time length and sampling rate significantly improves the accuracy of machine learning models compared to fixed time lengths. ATLO-ML shows potential for generalization across various time-sensitive applications, offering a robust solution for optimizing temporal input parameters in machine learning workflows.